Triple
T9722814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rose Smith |
E235520
|
entity |
| Predicate | creator |
P184
|
FINISHED |
| Object | Sally Benson |
E267156
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sally Benson | Statement: [Rose Smith, creator, Sally Benson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sally Benson Context triple: [Rose Smith, creator, Sally Benson]
-
A.
Sally Benson
chosen
Sally Benson was an American author and screenwriter best known for her semi-autobiographical stories that inspired the classic film "Meet Me in St. Louis."
-
B.
Sally Alexander
Sally Alexander is a British feminist historian and academic known for her work on women's history and social movements.
-
C.
Ellen Benson
Ellen Benson is the protagonist of the work titled "Suddenly."
-
D.
Sally Cobb
Sally Cobb was the wife of American Founding Father and Declaration of Independence signer Robert Treat Paine.
-
E.
Sally Crocker
Sally Crocker is a notable individual who shares the Crocker surname, recognized enough to be specifically cited as a bearer of the name.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ca84d0123c819096f9dc3b6abb0881 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9e75abd48190a6e6679ec51496e8 |
completed | April 1, 2026, 10:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f08ec96fe88190b791e6f50f39173f |
completed | April 28, 2026, 10:41 a.m. |
Created at: March 30, 2026, 8:20 p.m.